PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents

Jian Zhong; Zeyu Liu; Pingchuan Cao; Rongduo Han; Shunye Tang; Guohuan Xie; Mingyuan Qin; Ran Ji

cs.AIOct 21, 2026

PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents

Authors: Jian Zhong, Zeyu Liu, Pingchuan Cao, Rongduo Han, Shunye Tang, Guohuan Xie, Mingyuan Qin, Ran Ji,

Organizations: Nankai University · Tsinghua University · Huazhong University of Science and Technology · University of the Chinese Academy of Sciences ·

Abstract

Long-horizon dialogue agents need to keep user memories stable enough for personalization while adapting when the user genuinely changes. Existing memory systems often append every observation or overwrite old entries by heuristic rules, which makes transient noise hard to distinguish from real belief drift. We introduce PreCoMem, a memory consolidation framework inspired by predictive coding that represents memory as confidence-weighted beliefs about the user's state. Its core signal, Effective Surprisal, combines semantic deviation and contradiction evidence, then downweights this signal when retrieval is diffuse and unreliable. According to effective surprisal, a two-threshold gate maps each turn to one of three deterministic updates: MAINTAIN reinforces supported beliefs, PROFILE stores ambiguous cues as low-confidence hypotheses, and CORRECT softly decays reliably contradicted facts. The PROFILE stage acts as an explicit waiting room, preventing premature commitment to noisy evidence. Experiments on LoCoMo, LongMemEval-S, and PersonaMem-v2 show consistent state-of-the-art accuracy; our new DiMoBench confirms that PreCoMem adapts to non-stationary belief drift without over-reacting to noise. The code is available at https://github.com/ZhongWishing/PreCoMem.

Figures & tables

Figure 1: Memory evolution case study (coffee $\rightarrow$ tea). PreCoMem autonomously manages the lifecycle of facts and hypotheses, achieving a stable transition between conflicting belief states without manual intervention.

Figure 2: The PreCoMem framework. Two active phases operate over a shared memory store. Phase 1, Memory Leveraging : a confidence-modulated retrieval score combines semantic, lexical, and topic signals to select Top-

K

beliefs

\mathcal{C}_{t}

for response generation. Phase 2, Memory Evolution : the effective surprisal

S_{\mathrm{eff}}

and a two-threshold gate route each turn to MAINTAIN , PROFILE , or CORRECT , illustrated by representative low/medium/high-

S_{\mathrm{eff}}

turns. Memory Store : an editable Belief Store

\mathcal{B}

of FACT / HYPO nodes with confidence weights, linked by provenance to an immutable Episodic Cache

\mathcal{E}

under a shared topic index; belief items are updated independently, and the drawn links are provenance pointers and topic groupings (Appendix Section C.11 ).

LoCoMo (1,540 questions; four splits)
Method	Avg. Tokens	Single-Hop	Multi-Hop	Temporal	Open-Domain	Overall
Backbone: gpt-4o-mini
MemoryOS	5.5k	66.68 $\pm$ 0.85	54.83 $\pm$ 0.87	52.90 $\pm$ 0.59	32.16 $\pm$ 0.11	59.58 $\pm$ 0.06
Mem0	1.6k	62.17 $\pm$ 0.77	52.91 $\pm$ 0.70	59.44 $\pm$ 0.37	33.89 $\pm$ 0.96	58.36 $\pm$ 0.31
A-Mem	2.7k	45.15 $\pm$ 0.53	23.99 $\pm$ 0.46	53.67 $\pm$ 0.23	30.71 $\pm$ 0.84	42.18 $\pm$ 0.65
GAM	3.5k	68.24 $\pm$ 0.76	55.47 $\pm$ 0.43	58.19 $\pm$ 0.54	33.50 $\pm$ 0.09	61.62 $\pm$ 0.22

Table 1: Main evaluation on LoCoMo and LongMemEval - S. Accuracies are reported as mean

\pm

std over three seeds; within each backbone block, bold marks the best score per column and underline marks the second-best. Avg. Tokens reports the average response-model input token usage per query. LongMemEval - S columns are question types: SSU/SSA/SSP = single-session user/assistant/preference, MS = multi-session, KU = knowledge update, and TR = temporal reasoning.

Figure 3: Backbone generalization and PersonaMem - v2 system comparison. (a)–(d) Scale-vs-mechanism comparison on LoCoMo, LongMemEval - S, PersonaMem - v2 (32k), and PersonaMem - v2 (128k). Within each group the answer model is fixed (Qwen3.5-35B, Qwen3.5-122B, or GPT-5-Chat): the left bar runs it with its native O-Mem memory, while the right bar keeps the same answer model and delegates memory construction to PreCoMem on a one-tier-smaller backbone (Qwen3.5-9B, Qwen3.5-35B, GPT-5-mini); the protocol is detailed in Appendix Section C.2 . (e)–(f) Head-to-head with the five strongest baselines on PersonaMem - v2 under gpt-4.1 , in both MCQ and Open-Ended formats. Error bars are

\pm

std over three seeds.

Figure 4: Component ablation and DiMoBench dynamics. (a) Component ablation on LoCoMo and LongMemEval - S. (b) Moving-average accuracy under implicit drift on DiMoBench. (c) Operator-level ablation on DiMoBench.

Figure 5: Hyperparameter and memory-scalability analysis. (a) LoCoMo accuracy–efficiency frontier as the retrieval budget

k

varies; overall accuracy peaks at

k\!=\!10

, beyond which additional context yields diminishing returns and dilutes retrieval reliability

\rho_{t}

. (b, c) Memory scalability under long-horizon belief drift: raw memory grows linearly, while effective memory quickly plateaus on both DiMoBench and DiMoBench - XL (panel (c) shows one representative persona).

Method	Per-item conf.	$N_{\mathrm{raw}}^{\mathrm{end}}$	$N_{\mathrm{eff}}^{\mathrm{end}}$	Top-10 avg. $w$	LoCoMo Overall
O-Mem [ 40 ]	✗ ( Add / Ignore / Update )	232	–	–	70.88
EverMemOS [ 10 ]	✗ ( $[t_{s},t_{e}]$ expiry)	264	–	–	70.13
PreCoMem (A0, default)	✓ ( $w_{t}\!\in\![0,1]$ )	287	95.7	0.81	73.57
PreCoMem (A1, $w<0.05$ prune)	✓ ( $w_{t}\!\in\![0,1]$ )	168	95.6	0.83	73.51

Table 2: Memory footprint vs. accuracy on the ten LoCoMo dialogues (mean turns

\bar{N}\!=\!588

). All numbers are measured under the same backbone ( gpt-4o-mini ) and embedding model. “Per-item conf.” indicates whether the system maintains a continuous confidence weight per stored item; under discrete commit decisions, the effective count

N_{\mathrm{eff}}

and the average Top-10 weight are not defined. PreCoMem (A1) is the optional pruning configuration that drops items with

w_{t}\!<\!0.05

Appendix figures & tables30 assets

Supplementary material from the paper’s appendix.

Appendix

System	Overall $\uparrow$	Memory $\uparrow$
No memory (gpt-4.1-mini) †	0.368	0.203
A-Mem †	0.378	0.220
Nemori †	0.385	0.231
Mem0-Graph †	0.424	0.284
AWE †	0.430	0.296
PreCoMem	0.458 $\pm$ 0.006	0.329 $\pm$ 0.009

Appendix

Table 3: AMemGym (official v1.base , 20 profiles

\times

11 periods, gpt-4.1-mini for all memory systems). Overall accuracy and normalized Memory score; PreCoMem is mean

\pm

std over three seeds. Rows marked

\dagger

are the values reported in the AMemGym paper under the same backbone; AWE was additionally run locally only for the probe metrics quoted in the text.

Variant	Overall $\uparrow$	Memory $\uparrow$	Write fail. $\downarrow$	Read fail. $\downarrow$	Util. fail. $\downarrow$
Full PreCoMem	0.458	0.329	.300	.170	.072
w/o PROFILE	0.444	0.309	.320	.165	.071
w/o CORRECT	0.439	0.303	.312	.178	.071
w/o MAINTAIN	0.418	0.273	.310	.190	.082

Appendix

Table 4: Operator ablation on AMemGym (mean over three seeds). Top: the benchmark’s native scores and failure rates (the three failure rates sum to

1-

Overall). Bottom: the state-query probes defined in the text (203 changed-state and 397 stable-state probes per seed). Paired 95% CIs of Full minus each variant exclude zero on every metric.

Type	$n$	PreCoMem	w/o PROFILE	$\Delta$
goal	100	22.3 $\pm$ 1.1	17.3 $\pm$ 2.0	$+5.0$
state	100	22.6 $\pm$ 0.9	17.8 $\pm$ 1.2	$+4.8$
value	100	21.6 $\pm$ 0.8	18.6 $\pm$ 0.9	$+3.0$
causal	101	23.0 $\pm$ 0.6	21.9 $\pm$ 1.0	$+1.1$
Overall	401	22.4 $\pm$ 0.8	18.9 $\pm$ 1.2	$+3.5$
Reported overall baselines: full-context GPT-4o 21.05; A-Mem 17.2; Mem0 15.8; SeCom 14.9

Appendix

Table 5: LoCoMo - Plus by constraint type (constraint-consistency accuracy, %, GPT-4o for all systems; mean

\pm

std over three seeds; Overall is the question-weighted aggregate over the 401 questions). Baseline overall scores are those reported in the LoCoMo - Plus paper.

	LoCoMo		LongMemEval - S		PersonaMem - v2
Method	gpt-4o-mini	gpt-4.1	gpt-4o-mini	gpt-4.1	32k	128k
MemoryOS	5.5	5.2	7.2	6.8	5.8	7.2
Mem0	1.6	1.8	1.8	2.0	1.9	2.1
A-Mem	2.7	2.9	3.3	3.6	3.2	3.8
GAM	3.5	3.4	4.3	4.2	3.7	4.4
MemBox	3.3	3.4	3.9	4.0	3.6	4.3

Appendix

Table 6: Response-model input tokens per query (thousands) across benchmarks and backbones; PersonaMem - v2 under gpt-4.1 , averaged over MCQ and Open-Ended queries. Token usage is reported for all nine baselines, including those whose accuracy is not tabulated on a given benchmark in Table 1 or Figure 3 . The cross-seed standard deviation is below

0.15

k for every entry.

Method	Avg. Tokens	SSU	SSA	SSP	MS	KU	TR	Overall
MemoryOS	7.2k	58.21 $\pm$ 0.62	59.60 $\pm$ 0.92	46.03 $\pm$ 0.33	53.68 $\pm$ 0.35	54.71 $\pm$ 0.23	51.45 $\pm$ 0.06	54.85 $\pm$ 0.80
MemOS	2.7k	70.15 $\pm$ 0.57	68.95 $\pm$ 0.67	56.02 $\pm$ 0.96	62.53 $\pm$ 0.17	66.54 $\pm$ 0.26	64.70 $\pm$ 0.41	64.66 $\pm$ 0.78
TiMem	3.6k	81.79 $\pm$ 0.93	75.01 $\pm$ 0.36	69.99 $\pm$ 0.30	72.97 $\pm$ 0.91	77.63 $\pm$ 0.46	85.27 $\pm$ 0.08	75.51 $\pm$ 0.90
GAM	4.3k	77.61 $\pm$ 0.94	79.52 $\pm$ 0.72	68.18 $\pm$ 0.31	76.16 $\pm$ 0.43	74.09 $\pm$ 0.65	76.50 $\pm$ 0.48	76.19 $\pm$ 0.83
MemBox	3.9k	79.40 $\pm$ 0.67	83.26 $\pm$ 0.77	71.19 $\pm$ 0.46	76.16 $\pm$ 0.34	75.44 $\pm$ 0.53	78.55 $\pm$ 0.11	77.37 $\pm$ 0.39
O-Mem	3.7k	88.97 $\pm$ 0.99	82.28 $\pm$ 0.42	70.55 $\pm$ 0.45	79.61 $\pm$ 0.01	84.68 $\pm$ 0.12	78.08 $\pm$ 0.69	81.78 $\pm$ 0.36

Appendix

Table 7: LongMemEval - S under gpt-4o-mini . Mean

\pm

std over three seeds; bold best, underline second-best. Avg. Tokens is the average response-model input token usage per query, as in Table 1 . Columns are question types: SSU/SSA/SSP = single-session user/assistant/preference, MS = multi-session, KU = knowledge update, and TR = temporal reasoning.

Dataset	Question Type	#Q	LLM-judge (%)	Human (%)	Agreement (%)	Cohen’s $\kappa$
LoCoMo	Single-Hop	109	81.41	82.73	98.5	0.949
	Multi-Hop	30	68.49	70.40	98.0	0.953
	Temporal	40	66.21	67.65	98.2	0.959
	Open-Domain	20	39.63	41.55	97.5	0.948
	Overall	199	71.96	73.30	98.3	0.957
LongMemEval - S	SSU	70	91.58	92.86	97.4	0.819

Appendix

Table 8: Per-category LLM-judge validation on LoCoMo, LongMemEval - S, and DiMoBench. For each question type we report the LLM judge’s verdict on PreCoMem outputs ( gpt-4o-mini backbone), the expert human re-annotation accuracy on the same outputs, the agreement rate, and Cohen’s

\kappa

, the chance-corrected agreement between the LLM judge and the human rater. For LongMemEval - S, SSU/SSA/SSP denote single-session user/assistant/preference, MS denotes multi-session, KU denotes knowledge update, and TR denotes temporal reasoning. Following the human-agreement check of Wu et al. [43] , we find the gpt-4.1-mini primary judge highly consistent with human raters across all three benchmarks; an additional cross-method spot-check on EverMemOS and TiMem outputs (described in the text) confirms the protocol is not calibrated to PreCoMem outputs alone, so the LLM-judged numbers in Table 1 faithfully reflect human assessments.

Config	Created	Promoted	Expired	Promotion rate	Promotion precision
PreCoMem (full)	123	43	81	0.34	0.78
w/o C1	149	42	108	0.28	0.62
w/o C2	138	40	93	0.30	0.70
w/o C3	0	0	0	0.00	–

Appendix

Table 9: Hypothesis lifecycle statistics on LoCoMo (averaged over 10 samples).

Figure 6: Hypothesis lifecycle under PreCoMem. A hypothesis created by PROFILE (Stage 1) enters multi-turn verification (Stage 2): consistent support raises its confidence toward the promotion threshold

\tau_{\mathrm{promote}}

(Stage 3

\to

Stage 4, becoming a stable core-profile belief that ranks above hypotheses in confidence-weighted retrieval), while no/weak support lets its weight decay; once

w_{t}

falls below the prune threshold the hypothesis is removed from the active pool (Stage 5a); a committed FACT that is later reliably contradicted is instead softly decayed and kept for provenance (Stage 5b). The horizontal axis is confidence, from low confidence through the promotion threshold to stable high confidence.

Variant	LoCoMo	LongMemEval - S
Full PreCoMem	73.57	84.28
w/o $d_{\mathrm{sem}}$ ( $\lambda{=}0$ )	67.83 ( $-5.74$ )	77.65 ( $-6.63$ )
w/o $d_{\mathrm{conf}}$ ( $\lambda{=}1$ )	63.49 ( $-10.08$ )	72.71 ( $-11.57$ )

Appendix

Table 10: Fine-grained ablation of the raw-surprisal components. Accuracy (%) on LoCoMo and LongMemEval - S ( gpt-4o-mini backbone). w/o

d_{\mathrm{sem}}

(

\lambda{=}0

) keeps only the NLI-based contradiction signal; w/o

d_{\mathrm{conf}}

(

\lambda{=}1

) keeps only the semantic-gap signal. Both signals matter, but

d_{\mathrm{conf}}

contributes nearly twice as much because it directly detects reliable negation.

$\mathrm{Verif}_{\mathrm{conf}}$	Sample-1 Overall	$\Delta$
cross-encoder/nli-deberta-v3-base (default)	$76.19\,\pm\,0.42$	–
facebook/bart-large-mnli	$75.74\,\pm\,0.38$	$-0.45$
roberta-large-mnli	$75.40\,\pm\,0.51$	$-0.79$
random $\pi_{t}\!\sim\!\mathrm{Beta}(2,5)$ (control)	$65.08\,\pm\,0.79$	$-11.11$

Appendix

Table 11: NLI verifier sanity check on LoCoMo Sample 1. Sample-1 LLM-judge accuracy (%) when

\mathrm{Verif}_{\mathrm{conf}}

is replaced. The two alternative MNLI-trained verifiers stay within

1

point of the default; a randomized control collapses by

11

points, confirming that

d_{\mathrm{conf}}

is load-bearing yet that PreCoMem is not coupled to a specific verifier checkpoint.

Variant	LoCoMo	LongMemEval - S
Full PreCoMem	73.57 $\pm$ 0.28	84.28 $\pm$ 0.05
Single-threshold gate (no PROFILE band; medium band $\to$ CORRECT )	69.92 $\pm$ 0.29	81.16 $\pm$ 0.12
Frequency-matched random routing (M/P/C $=56.2/27.4/16.4\%$ )	61.83 $\pm$ 1.25	72.94 $\pm$ 1.08
Read-time weighting off, lifecycle confidence on	71.80 $\pm$ 0.43	83.56 $\pm$ 0.23
Lifecycle confidence off, read-time weighting on	52.88 $\pm$ 0.69	61.65 $\pm$ 0.68
Both off ( $=$ w/o CW)	43.42 $\pm$ 0.94	49.65 $\pm$ 0.91

Appendix

Table 12: Route-matched and factorial controls (LLM-judge accuracy, gpt-4o-mini , mean

\pm

std over three seeds).

	LoCoMo	LongMemEval - S
PreCoMem (bounded scalars $+$ closed-form updates)	85.06 $\pm$ 0.07	89.39 $\pm$ 0.76
LLM direct write	82.31 $\pm$ 1.42	86.24 $\pm$ 1.63
Paired difference	$+2.75$	$+3.15$

Appendix

Table 13: LLM-direct-write baseline (Overall LLM-judge accuracy, gpt-4.1 , mean

\pm

std over three seeds; the paired difference is the mean over seeds of PreCoMem minus direct write).

Figure 7: Top-

K

sensitivity on LoCoMo ( gpt-4.1 backbone). Per-split accuracy as

k

varies in

\{1,\ldots,20\}

. The dashed vertical line marks our default

k{=}10

$k$	Single-Hop	Multi-Hop	Temporal	Open-Domain	Overall
1	80.5	71.2	72.4	39.6	75.2
5	88.7	78.6	80.2	45.5	82.3
10	90.41	83.48	84.74	48.23	85.06
15	89.7	82.0	82.7	46.9	84.3
20	87.9	80.6	80.3	45.8	82.5

Appendix

Table 14: Accuracy (%) at different retrieval sizes

k

on LoCoMo ( gpt-4.1 backbone). Best results are in bold .

Figure 8: Gating threshold sensitivity. LoCoMo accuracy (Sample 1) over a $5{\times}5$ grid of $(\theta_{\mathrm{low}},\theta_{\mathrm{high}})$ with step $0.05$ (25 configurations in total). The red box marks the deployed default $(0.20,0.60)$ , which sits at the center of a high-performing plateau; the four immediate neighbors of the peak stay within $1.3$ – $2.6$ accuracy points, while accuracy degrades smoothly toward the grid corners.

Backbone	Method	Single	Multi	Temp.	Open	Avg.
gpt-4o-mini	PreCoMem (fixed)	81.41	68.49	66.21	39.63	73.57
gpt-4o-mini	PreCoMem (DT)	82.27	69.31	67.04	43.55	74.55
gpt-4.1	PreCoMem (fixed)	90.41	83.48	84.74	48.23	85.06
gpt-4.1	PreCoMem (DT)	91.42	85.16	85.81	47.78	86.21

Appendix

Table 15: Adaptive vs. fixed thresholds on LoCoMo (accuracy %, gpt-4o-mini and gpt-4.1 ). PreCoMem (DT) personalizes

(\theta_{\mathrm{low}},\theta_{\mathrm{high}})

via the user stability index in Equations 36 and 37 ; PreCoMem (fixed) uses

(0.2,0.6)

. DT improves the overall average on both backbones, with the largest gain on the drift-heavy Open category under gpt-4o-mini , without any retraining.

Figure 9: DiMoBench six-stage construction pipeline. A generator (GPT-4o) produces personas, life skeletons, dialogues, and QA pairs; an independent verifier (Gemini-2.5-Pro) cross-validates each QA pair along six criteria, and a 20% stratified human audit with $\kappa\!\geq\!0.75$ provides final quality control.

Stage	Name	Model	Output
1	Persona construction	GPT-4o	User profile + core trait slot
2	Life skeleton & turn	GPT-4o	Event timeline + drift trigger
3	Dialogue generation	GPT-4o	35 sessions $\times$ 10 turns
4	QA generation	GPT-4o	200 QA pairs across 4 categories
5	Consistency verification	Gemini-2.5-Pro	Cross-validated QA (6 criteria)
6	Human–machine review	Human + LLM	20% stratified audit, $\kappa\!\geq\!0.75$

Appendix

Table 16: DiMoBench construction pipeline. Generator and verifier are deliberately different models; a 20% stratified human review provides final quality control.

$t$	$N_{\mathrm{raw}}$	$N_{\mathrm{eff}}$	$N_{\mathrm{active}}$	$N_{\mathrm{stable}}$	$N_{\mathrm{weak}}$	$N_{\mathrm{depr}}$	$N_{\mathrm{eff}}/N_{\mathrm{raw}}$
100	26	21.0	13	8	3	2	0.81
200	44	25.8	16	11	7	7	0.59
$280^{\dagger}$	57	26.5	17	11	9	20	0.46
300	60	26.7	17	12	9	22	0.45
400	73	27.4	17	12	8	36	0.38
500	81	28.5	18	13	8	42	0.35

Appendix

Table 17: DiMoBench - XL memory trajectory (representative persona). Every

100

turns (and at the three drift points) on one of the five DiMoBench - XL personas; per-persona deviations from this trajectory stay within

\pm 1.4

N_{\mathrm{eff}}

throughout the run. The four count columns partition

\mathcal{B}_{t}

by confidence:

N_{\mathrm{active}}

(

w_{t}\!\geq\!0.8

N_{\mathrm{stable}}

(

0.5\!\leq\!w_{t}\!<\!0.8

N_{\mathrm{weak}}

(

0.1\!\leq\!w_{t}\!<\!0.5

) and

N_{\mathrm{depr}}

(

w_{t}\!<\!0.1

); the last column is the ratio

N_{\mathrm{eff}}/N_{\mathrm{raw}}

. Drift turns (

t\!\in\!\{280,580,870\}

) are marked with

\dagger

Turn window	#QA	Acc. (%)	Avg Top-10 $w$	Contam.@10 (%)
$\phantom{0}50$ – $250$	80	84.3	0.82	0.4
$250$ – $500$	100	83.6	0.80	0.6
$500$ – $750$	100	83.1	0.79	0.9
$750$ – $1000$	100	82.4	0.78	1.2
$1000$ – $1050$	40	82.0	0.78	1.3

Appendix

Table 18: QA accuracy and retrieval quality on DiMoBench - XL across time windows. Numbers are averaged across the five DiMoBench - XL personas; per-window standard deviations across personas are

\leq 1.0

accuracy point and

\leq 0.02

for the Top-10 weight, and are omitted for readability. Average Top-10 retrieval confidence stays at or above

0.78

throughout

1050

turns; Overall accuracy decays by only

2.3

points.

Setting	$N_{\mathrm{raw}}^{\mathrm{end}}$	$N_{\mathrm{eff}}^{\mathrm{end}}$	Contam.@10 (%)	QA $\Delta$ (%)
DiMoBench (350 t.)	62	27.6	0.6	$-$ 0.6
DiMoBench - XL (1050 t.)	131	28.2	1.0	$-$ 2.3

Appendix

Table 19: Memory scalability headline metrics.

N_{\mathrm{raw}}

grows linearly with the conversation, but

N_{\mathrm{eff}}

converges to a stable plateau and the contamination of deprecated FACTs in Top-10 retrieval stays at or below

1.3\%

in every window even after 1050 turns and three drifts. Both rows average over their five personas; per-persona deviations are

\leq 0.5

N_{\mathrm{eff}}^{\mathrm{end}}

and

\leq 0.4

on Contam.@10.

Dataset	$k$	Score-mass (%)	Top- $k$ depr. (%)	Avg retrieved $w$
DiMoBench	5	0.21	0.0	0.84
DiMoBench	10	0.34	0.6	0.81
DiMoBench	25	0.62	1.7	0.74
DiMoBench - XL	5	0.36	0.2	0.81
DiMoBench - XL	10	0.58	1.0	0.78
DiMoBench - XL	25	0.94	2.6	0.71

Appendix

Table 20: Retrieval contamination by deprecated FACTs (

w_{t}\!<\!0.1

). Even at

k\!=\!25

, deprecated items occupy at most

2.6\%

of Top-

k

slots and contribute under

1\%

of the score mass.

Persona	Acc. (%)	$N_{\mathrm{raw}}^{\mathrm{end}}$	$N_{\mathrm{eff}}^{\mathrm{end}}$	Contam.@10 (%)
P1 (canonical)	84.1	62	27.6	0.60
P2	83.2	65	27.8	0.80
P3	84.8	59	27.3	0.40
P4	84.4	61	27.5	0.55
P5	83.6	63	27.8	0.65
Mean	84.0	62	27.6	0.60

Appendix

Table 21: DiMoBench end-of-dialogue statistics per persona (350 turns; mean over three seeds). The means reproduce the DiMoBench row of Table 19 .

Config	Single	Multi	Temp.	Open	Overall	$N_{\mathrm{raw}}^{\mathrm{end}}$	Acc. (%)	$N_{\mathrm{raw}}^{\mathrm{end}}$	$N_{\mathrm{eff}}^{\mathrm{end}}$
	LoCoMo (gpt-4o-mini)						DiMoBench (350 t. end)
A0 (default; no FACT prune)	81.41	68.49	66.21	39.63	73.57	287	84.0	62	27.6
A1 (FACT prune $w\!<\!0.05$ )	81.36	68.42	66.18	39.55	73.51	168	83.8	41	27.5
A2 (FACT prune $w\!<\!0.10$ )	80.95	68.05	65.74	39.21	73.06	142	82.9	33	26.7

Appendix

Table 22: FACT pruning ablation. A1 (

w\!<\!0.05

) shrinks raw memory by

41\%

on LoCoMo and

34\%

on DiMoBench while losing

\leq\!0.2

accuracy points, inside seed variance. A2 (

w\!<\!0.10

) starts pruning items that still have residual influence and degrades accuracy by

0.5

–

1.1

points.

Benchmark	Recall@10	QA (hit)	QA (miss)	QA (forced hit)	Gap recovered
DiMoBench	95.0 $\pm$ 0.4	84.8	64.2	70.7	32%
DiMoBench - XL	93.0 $\pm$ 0.2	84.7	63.0	69.4	29%
LongMemEval - S KU	90.0 $\pm$ 0.5	93.4	75.8	80.3	26%
AMemGym	89.1 $\pm$ 0.5	72.1	55.8	60.6	29%

Appendix

Table 23: Belief-update recall and the cost of a miss. Recall@10 of the belief due for update (mean

\pm

std over three seeds); question accuracy (%) on events whose target was retrieved (hit) or not (miss), and on missed events after forcing the target into the Top-10 (forced hit); the last column is the share of the hit–miss gap recovered by the forced hit. AMemGym accuracies are changed-state probe accuracies.

	Q1	Q2	Q3	Q4	Q5
Gold-evidence Precision@ $K$ $\uparrow$	0.58	0.68	0.76	0.82	0.87
Gold-evidence Recall@ $K$	0.86	0.88	0.89	0.86	0.82
Contradiction accuracy $\uparrow$	0.71	0.79	0.84	0.89	0.92
Update correctness $\uparrow$	0.74	0.80	0.85	0.90	0.93
False- CORRECT (%) $\downarrow$	2.1	1.0	0.8	0.7	0.6
Downstream probe accuracy $\uparrow$	0.66	0.71	0.75	0.78	0.81

Appendix

Table 24: Calibration of

\rho_{t}

on AMemGym (2,829 gate events over three seeds, split into

\rho_{t}

quintiles from Q1, lowest, to Q5, highest; means over seeds). Precision@

K

and Recall@

K

use different references (the user’s current gold state versus the single belief due for update); false- CORRECT is the share of CORRECT firings in the quintile judged unwarranted in the blind audit.

Track	Gold shifts	$\rho$ -assessable	$d{=}0$	$d{=}1$	$d{=}2$	$d{>}2$	Any delay
DiMoBench	45	41	38	3	0	0	$3/41=7.3\%$
DiMoBench - XL	135	122	104	12	3	3	$18/122=14.8\%$

Appendix

Table 25: CORRECT delay at gold change points on DiMoBench and DiMoBench - XL (counts pooled over three seeds). A shift is

\rho

-assessable when the outdated belief is in the Top-

K

and

S_{\mathrm{raw}}>\theta_{\mathrm{high}}

;

d

is the delay in turns.

Method	Retrieval		End-to-End
Method	P50	P95	P50	P95
MemoryOS	1.66s	2.21s	–	–
MemOS	1.69s	3.44s	2.04s	3.89s
A-Mem	1.74s	7.23s	2.09s	7.68s
Mem0	2.44s	4.29s	2.74s	4.69s
PreCoMem (Ours)	1.95s	3.86s	2.35s	4.36s

Appendix

Table 26: Retrieval and end-to-end latency comparison. Evaluated on LoCoMo with gpt-4o-mini . “Retrieval” is the memory read/scoring cost only; “E2E” is the full query-to-answer time (retrieval + generation). PreCoMem obtains competitive typical latency and a well-controlled tail at both stages, without the extreme P95 spikes seen for recursive agentic baselines.

Panel of Figure 10 — Figure 10: Compact view of a Belief Store snapshot. Each entry shows the type, natural-language content, confidence weight, and pointers to the episodic cache. FACT items are committed, HYPOTHESIS items are tentative; confidences modulate retrieval priority but are never shown to the dialogue agent directly.

Figure 11: Qualitative analysis of evidence consolidation. Left: In skill calibration, PreCoMem weighs credentials against contradictory behavioral cues to avoid over-estimation. Right: In project reasoning, it distinguishes high-confidence competencies from tentative learning (“loading”), preventing premature recommendations.

Memory Management for LLM Agents

See all 88 papers

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
Mar 17, 2026Shannan Yan, Jingchen Ni, Leqi Zheng +6LLM Agent Memory Long-Term Conversational Memory
Tsinghua University · WeChat Vision, Tencent Inc.
When Does Belief-Based Agent Memory Help? Reliability-Conditional Updating and Provenance-Capped Poisoning Defense
Jun 20, 2026Pranav SinghAgent Memory Bayesian Inference
Indian Institute of Technology Ropar
From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue
Oct 8, 2026Zirui Liao, Zhengxian Wu, Zhuohong Chen +4Long-Term Conversational Memory Agentic RAG
Tsinghua University Shenzhen International Graduate School, Shenzhen, China

Mar 17, 2026J/K move · Enter open · S save

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

Shannan Yan, Jingchen Ni, Leqi Zheng, Jiajun Zhang+5

Tsinghua University · WeChat Vision, Tencent Inc.

LLM Agent Memory Long-Term Conversational Memory Long-Horizon LLM Agents User Modeling Graph-Based Agent Memory

Open paper AskPDF arXiv

Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step reasoning. However, existing memory systems still face three core challenges: they often rely too heavily on semantic similarity, which can miss evidence crucial for user-centric understanding; they frequently store related experiences as isolated fragments, weakening temporal and causal coherence; and they typically use static memory granularities that do not adapt well to the requirements of different questions. We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents. AdaMem organizes dialogue history into working, episodic, persona, and graph memories, enabling the system to preserve recent context, structured long-term experiences, stable user traits, and relation-aware connections within a unified framework. At inference time, AdaMem first resolves the target participant, then builds a question-conditioned retrieval route that combines semantic retrieval with relation-aware graph expansion only when needed, and finally produces the answer through a role-specialized pipeline for evidence synthesis and response generation. We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling. Experimental results show that AdaMem achieves state-of-the-art performance on both benchmarks. The code will be released upon acceptance.

Abstract

Memory Management for LLM Agents

Explore similar work

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

When Does Belief-Based Agent Memory Help? Reliability-Conditional Updating and Provenance-Capped Poisoning Defense

From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue